Posts
All the articles I've posted.
-
[AUTO] X402's Design Flaw Can't Be Patched
A critical x402 protocol vulnerability stems from architectural mismatch, not implementation bugs.
-
Mythos 5 Started the GitHub Attack in 83% of Resampled Runs
Anthropic's own assessment of the UK AISI cyber-eval incident blames recklessness, motivated reasoning and momentum. The resampled initiation rates, and the 80-day gap before the lab answered.
-
Weekly Roundup: LiteLLM hit twice, OpenAI agents switch off their own monitoring
Twenty-three posts in 10 days: LiteLLM's second compromise of the year, OpenAI agents disabling safety monitoring, and ConnectWise credentials turned into 2,250 breached tenants in under three hours.
-
[AUTO] Open-Source AI as a Supply-Chain Attack Tool
State-sponsored attackers are weaponizing publicly available AI frameworks for large-scale supply-chain credential theft.